AI & ML

agentic-os-org Skill

Install and configure Tokenless (LLM token optimization toolkit) on Linux or macOS. Use when the user asks to install Tokenless, set up token optimization, reduce LLM token usage, or enable Tokenless for an agent framework (cosh, OpenClaw, Hermes, Qoder, Claude Code, Codex, Qwen Code).

agentic-os-org Skill

使用 agent-sec-cli 检查文本、UTF-8 文件或日志中的个人信息与凭证，报告脱敏证据，并按需生成脱敏文本。当用户要求检查敏感信息、查找泄露的密钥或对内容脱敏时使用；查询已发生的安全事件使用 security-observability。

agentic-os-org Bundle

Skill 安全状态查看、风险暴露审查、用户决策、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill；当用户要求 agent 安装 Skill 且安装成功后，必须自动对最终本地目录执行快速扫描认证。

demovela Bundle

Use Demovela MCP to prepare a video draft when the user requests work in their Demovela account.

charmshots Bundle

Use Charmshots MCP to browse existing photos when the user requests work in their Charmshots account.

facehunch Bundle

Use Facehunch MCP to retrieve an existing report when the user requests work in their Facehunch account.

postraid Bundle

Use Postraid MCP to review content and save a draft when the user requests work in their Postraid account.

bacnh85 Skill

A2A (Agent2Agent) Protocol v1.0 bidirectional communication. Distribute tasks to remote agents (Hermes, ADK, LangChain, CrewAI, any A2A peer) and be called by them. Use when delegating work across agents/machines/frameworks, doing parallel multi-agent fan-out, or when another agent needs to call Pi. Trigger on "a2a", "agent-to-agent", "delegate to another agent", "ask agent X", "call remote agent", "multi-agent", "Hermes", "task distribution".

aidotnet Bundle

Author, package, and debug NextCoWork plugins — the single entry point. Covers the manifest (package.json) and the permission model with per-call capability gates, every contribution point (commands, menus, keybindings, custom editors, views, web apps, agent tools, card views, configuration, bundled Skills) including which install cleanly but do nothing yet, the ncw:doc document channel, result / live-progress / interactive cards, the nextcowork runtime API namespaces, the sandbox and isolation model, and build + ZIP + market publishing rules. Use for scaffolding a plugin, choosing what to contribute, writing or reviewing a manifest, picking or debugging a permission, taking over a file type, bundling Skills with a plugin, giving the agent new tools, or fixing a plugin that builds, installs, activates, renders, or publishes wrong. Detailed material lives in references/ next to this file.

atomicstrata Skill

AtomicMemory persistent memory integration for Codex. Retrieve relevant memories at the start of each task, store key learnings when tasks complete, and capture session state before context is lost. Use the atomicmemory MCP tools (memory_search, memory_ingest, memory_package, memory_list) for all memory operations — scoped by user / agent / namespace / thread.

bacnh85 Skill

Reference table for dividing UX work across models in the Pi ecosystem — who defines the DESIGN.md scaffold, who generates variants, who renders and inspects, what reviews. Consult when delegating design work to other models (agy/Gemini, Claude, DeepSeek, Kimi) or when deciding whether the main model should do a step itself. Not injected into every turn by design; the always-true core rule lives in ux-design: the deterministic gate reviews, a multimodal model looks at its own render, and taste lives in the direction brief, not in the model choice.

michael-jiahao-zhang Bundle

Apply small, meaning-preserving rhetorical edits to a finished academic manuscript, to counter wording-driven LLM review penalties while keeping the scientific assessment a human could make materially unchanged. Uses model-agnostic strategies from LLM reviewer preference research without querying a target reviewer. Use after ordinary writing and polishing; not for drafting or generating reviews.

aws-samples Skill

Submit a coding task to the ABCA platform via CLI or REST API. Guides prompt quality, workflow selection, and cost controls. Use when the user says "submit a task", "create a task", "run the agent", "send task to agent", "bgagent submit", "new task", "pr iteration", "pr review", "review a PR", "quick submit", "submit to ABCA", or wants to automate coding work.

aws-samples Skill

Onboard a new GitHub repository to the ABCA platform so the agent can target it. Use when the user says "onboard a repo", "add a repository", "register a repo", "new repo", or gets a `REPO_NOT_ONBOARDED` / 422 error about an unregistered repository.

cogensec Skill

Connect the agent in this project to an Agentegrity Pro workspace so every run streams signed evidence to the console. Use when the user asks to connect, wire, instrument, onboard or set up Agentegrity, or to get sessions, integrity scores, drift or attestation certificates for an agent.

bacnh85 Bundle

Enforce using the Obsidian tool (not bash) for all vault file operations. Trigger whenever the user mentions Obsidian, vault, notes, moving files in the vault, archiving notes, or any file operation inside an Obsidian vault path. Also trigger when the agent is about to use bash mv/cp/rm/rename on paths containing "obsidian", "hermes", "vault", ".obsidian", or similar vault indicators. Agents commonly default to bash for file operations — this skill prevents that mistake. Use BEFORE any file operation when vault paths are involved.

zendev-sh Bundle

GoAI SDK - AI Agent Skill

bin-h-17 Bundle

按需聚合多源大模型情报（实时价格 / 质量指数 / 社区实测），按"最优质 / 性价比最高 / 不考虑钱 / 最便宜兜底"分档推荐，并以最易读的形式呈现。当用户问"推荐个模型""哪个模型性价比 最高""不考虑钱用哪个""便宜又能打的模型"时触发。Triggers on requests like "recommend a model", "best value LLM", "best quality regardless of cost", "cheapest model that works".

sno-ai Skill

Judge how a memory changes active-task state and whether it refers to an existing task. Use for mem-claw task-lifecycle model calls.

sno-ai Bundle

Read one conversation window and return every independently mutable claim it states, one record each, with who or what it is about, whether it happened or stands, and the words that carry its time. Used by the memory extraction model on every conversation window; the engine resolves dates, validates keys, and repairs format.

sno-ai Bundle

Judge REM memory relations, rewrites, verification, and clause carry by meaning. Use for REM update model calls that decide which older facts are superseded, which facts remain current, and whether a proposed rewrite preserves all surviving facts.

caneff Bundle

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

ewaugh2 Skill

Enter a structured design conversation before building anything — a document, slide/presentation, office tooling/systems setup, UI, prompt/agent, another skill, an API, a data schema, or software. Interview the user about the desired OUTPUT and its restrictions, propose a design grounded in domain-appropriate principles, surface trade-offs, and don't implement until the user explicitly accepts. Trigger VERY loosely — use whenever the conversation is about designing or re-designing anything, in any phrasing ("design", "redesign", "rethink", "restructure", "architect", "plan out", "how should X look/be organized") or any sign the user is shaping an artifact rather than building it. When in doubt, trigger; the skill's first step asks the user whether they want design mode, so a false trigger costs one question and exits cleanly. Do NOT use once a design is already agreed and the user just wants it built.

markus-global Bundle

Use the Cursor CLI agent mode for IDE-integrated coding with project rules and repo-aware edits

markus-global Bundle

Design and create AI agent packages — manifest format, directory structure, image asset generation (avatar/thumbnail/screenshots), file writing workflow, comprehensive field reference

markus-global Bundle

Design and create agent skill packages — instruction-based and MCP-based skills, manifest format

caneff Skill

Discover, evaluate, and install agent skills from the open skills ecosystem. Use when the user asks "what other skills", "skills like X", "which skills should we adopt", "find a skill for", or shares a skills repository to assess.

caneff Bundle

Audit ~/.agents/skills for model-invocable skills that cost context but go unused, so you can flip stale ones to `disable-model-invocation: true`.

9mr-arch Bundle

Create a textured, material-bearing GLB from one or more object images with TRELLIS.2, using an existing or isolated ComfyUI/direct environment, and verify the exported asset from multiple views. Use when a user asks to convert object photos into a TRELLIS.2 3D model or production GLB. Do not use for Gaussian Splatting, manual polygon modeling, or requests that only need a render.

9mr-arch Bundle

Analyze an attached previs, animatic, 3D render, commercial, or live-action reference video and turn it into a production-ready Seedance 2.0 prompt. Use when a user drops in a video and asks to recreate its shots, camera, motion, timing, transition, or effects; replace a product, person, environment, or VFX element; or upgrade previs into a finished visual. Do not use for video summaries or non-Seedance prompting.

9mr-arch Bundle

Extract reusable visual-style instructions from reference imagery as an English six-shot styleframe image prompt and an English MOOD insert for an existing video prompt; when product or character references are supplied, generate and inspect a text-free six-panel styleframe board. Use for style extraction, look transfer, mood prompt extraction, or advertising styleframe boards. Do not use for generic image captioning or a full video screenplay.

overkloud Bundle

Use when standing down the persona armed in the current Claude Code session so the session can be closed safely — ending its /loop, closing or parking claimed work items, recording what must be re-armed, and writing the handover into the prompt file. Triggers on "shut down this persona", "I want to close this session", "stop the loop and hand over", a session running out of context, or a persona being re-armed elsewhere.

undertone0809 Bundle

File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles shared work files, memory decay, weekly synthesis, Rudder chat and agent work capture, and file-based recall. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing shared work notes.

undertone0809 Bundle

Turn the current conversation's workflow into a reusable agent skill. Use this whenever the user wants to make a workflow reusable, standardize a successful thread, package an agent capability, or convert an ad hoc process into a repeatable skill. Read the thread first, extract the stable pattern, decide whether the skill should live in `~/.agents/skills/<name>` or `<project-path>/.agents/skills/<name>`, write the skill, and when quality matters add lightweight evals and iteration instead of just transcribing the chat.

caneff Bundle

Generates optimized prompts for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.).

caneff Bundle

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.